What is it about?
Morphing is a technique used to generate a progressive deformation from one object to another. The work proposed in this article focuses on morphing between objects within the same category to generate new objects that retain the same semantic meaning. This generation process serves as a powerful data augmentation method, enhancing the performance of machine learning classification models.
Featured Image
Photo by Growtika on Unsplash
Why is it important?
The importance of this approach lies in the non-linearity of the data augmentation process, which generates data that have the same meaning as the original ones but undergo non-linear transformations.
Perspectives
The perspectives are to apply this paradigm to multiple data types, including 3D point clouds, RGB face images, and more.
Emna Ghorbel
Universite de la Manouba
Read the Original
This page is a summary of: Data augmentation based on shape space exploration for low-size datasets: application to 2D shape classification, Neural Computing and Applications, April 2024, Springer Science + Business Media,
DOI: 10.1007/s00521-024-09798-5.
You can read the full text:
Resources
Contributors
The following have contributed to this page
